Qi Song

Nanyang Technological University, Northeastern University

Papers

Total Citations

H-Index

About

Qi Song’s research bridges the critical intersection of intelligent control systems, robotics, and wireless sensor networks, with a particular focus on fault tolerance and robust estimation. His most influential work, “Robust adaptive fault accommodation for a robot system using a radial basis function neural network” (2001, 6 citations), pioneered a discrete-time RBF neural network approach that leverages an adaptive dead-zone technique to ensure convergence in robotic fault accommodation—a foundational contribution to resilient automation. Song further advanced control theory with his 2003 study on a robust neural network/proportional tracking controller, which guaranteed global stability through sector theory and a normalized learning algorithm, eliminating the need for bounded regression signals. More recently, his 2020 work on mobile localization in the Internet of Things (4 citations) introduced a robust extended Kalman filter combined with improved M-estimation to mitigate non-line-of-sight propagation errors in wireless sensor networks, addressing a critical challenge in IoT localization. Across these contributions, Song demonstrates a consistent commitment to developing theoretically rigorous, practically deployable algorithms that enhance system reliability and accuracy, making his research valuable for engineers and researchers working on autonomous systems, networked control, and smart environments.